• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ½ºÆ®¸² µ¥ÀÌÅÍ ÇнÀÀ» À§ÇÑ ¿¹ÃøÀû ÄÁº¼·ç¼Ç ½Å°æ¸Á
¿µ¹®Á¦¸ñ(English Title) Predictive Convolutional Networks for Learning Stream Data
ÀúÀÚ(Author) Çã¹Î¿À   À庴Ź   Min-Oh Heo   Byoung-Tak Zhang  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 11 PP. 0614 ~ 0618 (2016. 11)
Çѱ۳»¿ë
(Korean Abstract)
ÀÎÅÍ³Ý »ó µ¥ÀÌÅÍ¿Í ½º¸¶Æ® µð¹ÙÀ̽º°¡ Áõ°¡ÇÔ¿¡ µû¶ó ¼øÂ÷ÀûÀ¸·Î À¯ÀԵǴ ½ºÆ®¸² Çü½ÄÀÇ µ¥ÀÌÅÍ°¡ ´Ã¾î³ª°í ÀÖ´Ù. ÀáÀçÀûÀÎ ºòµ¥ÀÌÅÍÀÎ ½ºÆ®¸² µ¥ÀÌÅ͸¦ ´Ù·ç±â À§Çؼ­´Â ¿Â¶óÀÎ ÇнÀÀÌ °¡´ÉÇØ¾ß ÇÑ´Ù. ÀÌ¿¡ º» °í¿¡¼­´Â ½ºÆ®¸² µ¥ÀÌÅÍ ÇнÀÀ» À§ÇÑ »õ·Î¿î ¸ðµ¨ÀÎ ¿¹ÃøÀû ÄÁº¼·ç¼Ç ½Å°æ¸Á°ú ¿Â¶óÀÎ ÇнÀ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ÀÌ ¸ðµ¨Àº ŽÁö¿Í Ç®¸µÀ» ¹Ýº¹ÇÏ´Â ÄÁº¼·ç¼Ç ¿¬»êÀ» ÅëÇØ Å½Áö ÆÐÅÏÀ» °èÃþÈ­ÇÏ¿© »óÀ§°èÃþÀÌ µÉ¼ö·Ï ±ä ±æÀÌÀÇ ÆÐÅÏÀÇ Á¤º¸¸¦ ´Ù·çµµ·Ï ÇÑ´Ù. º» ¸ðµ¨ÀÇ ±âÃÊÀû °ËÁõÀ» À§ÇØ ½º¸¶Æ®ÆùÀ¸·Î 2 ´Þ°£ ¼öÁýÇÑ GPS µ¥ÀÌÅ͸¦ ÀÌ»êÈ­ÇÏ¿© °üÃøµ¥ÀÌÅÍ·Î »ï¾Ò´Ù. À̸¦ Á¦¾È¸ðµ¨À» ÅëÇØ ÇнÀÇÏ¿© °èÃþÀ» µû¶ó Ãß»óÈ­µÈ Á¤º¸·ÎºÎÅÍ º¹¿øÇÑ µ¥ÀÌÅÍ¿Í °üÃøµ¥ÀÌÅ͸¦ ºñ±³ÇÏ¿©, ±ä ½Ã°£ÀÇ ÆÐÅÏÀ» ´Ù·ç¸é¼­µµ °üÃø ¼öÁØÀÇ µ¥ÀÌÅ͸¦ º¹¿øÇÏ´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
As information on the internet and the data from smart devices are growing, the amount of stream data is also increasing in the real world. The stream data, which is a potentially large data, requires online learnable models and algorithms. In this paper, we propose a novel class of models: predictive convolutional neural networks to be able to perform online learning. These models are designed to deal with longer patterns as the layers become higher due to layering convolutional operations: detection and max-pooling on the time axis. As a preliminary check of the concept, we chose two-month gathered GPS data sequence as an observation sequence. On learning them with the proposed method, we compared the original sequence and the regenerated sequence from the abstract information of the models. The result shows that the models can encode long-range patterns, and can generate a raw observation sequence within a low error.
Å°¿öµå(Keyword) ½ºÆ®¸² µ¥ÀÌÅÍ   ¿¹ÃøÀû ÄÁº¼·ç¼Ç ½Å°æ¸Á   ½ÃÄö½º ÇнÀ   ¿Â¶óÀÎ ÇнÀ   stream data   convolutional neural networks   sequence learning   online learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå